Comments on 'Fractional Extreme Value Adaptive Training Method: Fractional Steepest Descent Approach'

Abdul Wahab; Shujaat Khan

doi:10.1109/TNNLS.2019.2899219

Comments on 'Fractional Extreme Value Adaptive Training Method: Fractional Steepest Descent Approach'

Abdul Wahab^*
, Shujaat Khan

^*Corresponding author for this work

Research output: Contribution to journal › Review article › peer-review

8 Scopus citations

Abstract

In this comment, we raise serious concerns over the derivation of the rate of convergence of fractional steepest descent algorithm in fractional adaptive learning approach presented in 'Fractional Extreme Value Adaptive Training Method: Fractional Steepest Descent Approach.' We substantiate that the estimate of the rate of convergence is grandiloquent. We also draw attention toward a critical flaw in the design of the algorithm stymieing its applicability for broad adaptive learning problems. Our claims are based on analytical reasoning supported by experimental results.

Original language	English
Article number	8666136
Pages (from-to)	1066-1068
Number of pages	3
Journal	IEEE Transactions on Neural Networks and Learning Systems
Volume	31
Issue number	3
DOIs	https://doi.org/10.1109/TNNLS.2019.2899219
State	Published - Mar 2020
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2012 IEEE.

Keywords

Fractional calculus
fractional differential
fractional energy norm
fractional extreme point
fractional gradient

ASJC Scopus subject areas

Software
Computer Science Applications
Computer Networks and Communications
Artificial Intelligence

Access to Document

10.1109/TNNLS.2019.2899219

Cite this

@article{f65c407b13014878b74d6906715586ea,

title = "Comments on 'Fractional Extreme Value Adaptive Training Method: Fractional Steepest Descent Approach'",

abstract = "In this comment, we raise serious concerns over the derivation of the rate of convergence of fractional steepest descent algorithm in fractional adaptive learning approach presented in 'Fractional Extreme Value Adaptive Training Method: Fractional Steepest Descent Approach.' We substantiate that the estimate of the rate of convergence is grandiloquent. We also draw attention toward a critical flaw in the design of the algorithm stymieing its applicability for broad adaptive learning problems. Our claims are based on analytical reasoning supported by experimental results.",

keywords = "Fractional calculus, fractional differential, fractional energy norm, fractional extreme point, fractional gradient",

author = "Abdul Wahab and Shujaat Khan",

note = "Publisher Copyright: {\textcopyright} 2012 IEEE.",

year = "2020",

month = mar,

doi = "10.1109/TNNLS.2019.2899219",

language = "English",

volume = "31",

pages = "1066--1068",

journal = "IEEE Transactions on Neural Networks and Learning Systems",

issn = "2162-237X",

publisher = "IEEE Computational Intelligence Society",

number = "3",

}

TY - JOUR

T1 - Comments on 'Fractional Extreme Value Adaptive Training Method

T2 - Fractional Steepest Descent Approach'

AU - Wahab, Abdul

AU - Khan, Shujaat

PY - 2020/3

Y1 - 2020/3

N2 - In this comment, we raise serious concerns over the derivation of the rate of convergence of fractional steepest descent algorithm in fractional adaptive learning approach presented in 'Fractional Extreme Value Adaptive Training Method: Fractional Steepest Descent Approach.' We substantiate that the estimate of the rate of convergence is grandiloquent. We also draw attention toward a critical flaw in the design of the algorithm stymieing its applicability for broad adaptive learning problems. Our claims are based on analytical reasoning supported by experimental results.

AB - In this comment, we raise serious concerns over the derivation of the rate of convergence of fractional steepest descent algorithm in fractional adaptive learning approach presented in 'Fractional Extreme Value Adaptive Training Method: Fractional Steepest Descent Approach.' We substantiate that the estimate of the rate of convergence is grandiloquent. We also draw attention toward a critical flaw in the design of the algorithm stymieing its applicability for broad adaptive learning problems. Our claims are based on analytical reasoning supported by experimental results.

KW - Fractional calculus

KW - fractional differential

KW - fractional energy norm

KW - fractional extreme point

KW - fractional gradient

UR - https://www.scopus.com/pages/publications/85081593406

U2 - 10.1109/TNNLS.2019.2899219

DO - 10.1109/TNNLS.2019.2899219

M3 - Review article

C2 - 30872244

AN - SCOPUS:85081593406

SN - 2162-237X

VL - 31

SP - 1066

EP - 1068

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

IS - 3

M1 - 8666136

ER -

Comments on 'Fractional Extreme Value Adaptive Training Method: Fractional Steepest Descent Approach'

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this